Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0000

Data Index: 504782 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5265. Min Act: -0.0000

Data Index: 53944 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4980. Min Act: -0.0000

Data Index: 933594 (The Pile)

Max Activating Token Index: 208

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1259316 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4942. Min Act: -0.0000

Data Index: 894845 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1245205 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4700. Min Act: -0.0000

Data Index: 947472 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1159566 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4120. Min Act: -0.0000

Data Index: 228626 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1435109 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3887. Min Act: -0.0000

Data Index: 905108 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3960. Min Act: -0.0000

Data Index: 558273 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1859658 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1969025 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1860479 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1460024 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1320168 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1444347 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3612. Min Act: -0.0000

Data Index: 557524 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1761887 (The Pile)

Max Activating Token Index: 901